Files
PlantAI-rag/docs/EXTRACTORS_INDEX.md
2026-07-10 17:59:59 +08:00

63 lines
1.7 KiB
Markdown
Executable File
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# 提取器索引
根目录提取器已归档到 `extractors/` 目录。
## 📁 提取器分类
### current/fusion/ - PC融合版(当前使用)
- extractor_fusion_complete.py - **主提取器**,8种实体,7种关系
- extractor_fusion_v1.py - 融合版v1(备份)
### current/llm/ - LLM提取器(当前使用)
- llm_extractor_dashscope.py - 百炼API提取
- llm_extractor_simple.py - 简单LLM提取
- llm_extractor_v2.py - LLM提取v2
- llm_relation_extractor.py - LLM关系提取
- universal_extractor_v2.py - 通用提取器v2
### archive/ - 归档版本(不再维护)
#### SUC5系列(早期实验)
- extractor_suc5.py
- extractor_suc5_v2.py
- extractor_suc5_v3.py
- extractor_suc5_v4.py
- extractor_suc5_final.py
- extractor_suc5_pc_match.py
#### PC实验版
- extractor_pc_122_types.py
- extractor_pc_complete.py
- extractor_pc_complete_types.py
- extractor_pc_entities.py
- extractor_pc_entities_v2.py
- extractor_pc_full_types.py
- extractor_pc_style.py
- extractor_pc_v2.py
#### 其他旧版
- extractor_complete_v1.py
- extractor_enhanced.py
- extractor_final.py
- extractor_hybrid.py
- extractor_hybrid_v3.py
- extractor_llm_v1.py
- extractor_production_v1.py
- extractor_v2_pro.py
- universal_extractor_v1.py
## 📄 根目录保留
- extractor_pc_based.py - PC规则版(有硬编码路径依赖)
- EXTRACTORS_INDEX.md - 本文档
## 🎯 推荐使用
| 场景 | 推荐提取器 | 位置 |
|------|-----------|------|
| 对标PC | extractor_fusion_complete.py | extractors/current/fusion/ |
| LLM提取 | llm_extractor_dashscope.py | extractors/current/llm/ |
| PC规则 | extractor_pc_based.py | 根目录 |
---
*归档时间:2026-04-12*